June 2024 Unit 2 Q4
4. A company produces sweets of varying colours. The company claims that the proportion of blue sweets is 13·6%. A consumer believes that the true proportion is less than this. In order to test this belief, the consumer collects a random sample of 80 sweets.
(a) State suitable hypotheses for the test. [1]
(b)
(i) Determine the critical region if the test is to be carried out at a significance level as close as possible to, but not exceeding, 5%.
(ii) Given that there are 6 blue sweets in the sample of 80, complete the significance test. [5]
(c) Suppose the proportion of blue sweets claimed by the company is correct. The consumer conducts the sampling and testing process on a further 20 occasions, using the sample size of 80 each time. What is the expected number of these occasions on which the consumer would reach the incorrect conclusion? [2]
(d) Now suppose that the proportion of blue sweets is 7%. Find the probability of a Type II error. Interpret your answer in context. [3]
| Scheme | Marks | Comments |
|---|---|---|
| \(H_0\colon p=0.136\) \(H_1\colon p<0.136\) | B1 | Allow use of \(\theta\) Condone other letters if defined as proportion/prob. Allow \(H_0\colon \text{P(blue)}=0.136\), \(H_1\colon \text{P(blue)}<0.136\) Allow 13.6% (B0 for \(p=13.6\)) B0 for non-strict inequality in \(H_1\) B0 for omission of \(p\) (oe) [e.g. \(H_0=0.136\)] B0 for \(H_0\colon x=0.136\) or \(H_0\colon \text{P}(X=0.136)\) B0 for hypothesis labels omitted Allow worded hypotheses (must refer to proportion/prob.). Do not award retrospectively from (b). |
| [1] |
| Scheme | Marks | Comments |
|---|---|---|
| (i) Under \(H_0\), \(X\sim\text{B}(80,0.136)\) | B1 | si |
| \(\text{P}(X\le 5)=0.0309\) and/or \(\text{P}(X\le 6)=0.0690\) | M1 | M0 for \(\text{P}(X=5)\) or \(\text{P}(X=6)\). |
| CR \((0\le)X\le 5\) | A1 | Do not accept as probability statement, i.e. \(\text{P}(X\le 5)\) is the CR. |
| (ii) 6 is not in the critical region so there is insufficient evidence to reject \(H_0\). | M1 | FT their CR for M1 (provided a region) Accept \(\text{P}(X\le 6)=0.06902>0.05\) as justification to not reject \(H_0\). M0 for \(\text{P}(X=6)\). |
| There is insufficient evidence to suggest that the proportion of blue sweets is less than the company’s claim. | A1 | CSO (all previous marks in (b) awarded) |
| [5] |
| Scheme | Marks | Comments |
|---|---|---|
| \(\text{P(reject }H_0)=\text{P}(X\le 5)=0.0309\) Expected number of occasions \(=20\times 0.0309\) | M1 | FT the probability of their CR for M1A1 provided a region |
| \(=0.618\) | A1 | A0 for sight of 1 only without seeing 0.618 SC1 for \(20\times 0.05=1\) |
| [2] |
| Scheme | Marks | Comments |
|---|---|---|
| Prob (Type II error) = \(\text{P}\big(X\ge 6\,|\,X\sim\text{B}(80,0.07)\big)\) | M1 | si FT their CR provided a region for M1A1 |
| \(=0.49183\) | A1 | 3sf or better |
| Valid interpretation. e.g. There is almost a 50% chance of failing to detect that the proportion of blue sweets is less than the company’s claim (when in fact it is 7%). e.g. The probability of failing to reject the hypothesis that the proportion of blue sweets is not less than the company’s claim when, in fact, it should have been rejected is almost 50%. e.g. There is a 49.183% chance of supporting the company’s claim when in fact it is false. e.g. There is a 49.183% chance of concluding the proportion of blue sweets has not reduced, when in fact it has. | E1 | FT their Type II error (even if M0 awarded). E0 for “You would make the wrong decision almost 50% of the time.” E0 for “There is almost a 50% chance that the company makes a false negative.” E0 for “This error probability is too large” or “this is not a good test”. |
| [3] | ||
| Total for Question | 11 |